NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KB8RMP4EN3ZWGV02G7TN55
Run Details
Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
59.9s
Cost:
$0.017295
Provider:
Together
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly unfolded a glittery napkin map of the community center, tapping the bouncy castle with a stolen lollipop. Bill adjusted his rainbow wig, which smelled of old balloons and very poor decisions. "We go as clowns," she whispered. "You juggle, I swipe gifts." Bill frowned at his slightly oversized shoes. "What if the kids cry?" Molly shrugged. "We cry louder, then we run." She quickly folded the map into a paper hat and jammed it on his head. The plan was simple: arrive during the piƱata frenzy, when parents were a little too busy filming to notice two extra clowns waddling toward the present table. Bill would drop his juggling balls into the punch bowl as a distraction. Molly would fill a garbage bag with wrapped boxes, honk a horn, and immediately vanish through the bouncy castle's emergency exit. They had always stolen many things over the years, but never from people whose emotional attachment was still in the gift wrap. Bill nervously practiced his sad clown face. It looked exactly like his planning face. Molly handed him a whoopee cushion and patted his shoulder twice. He squeezed it once. The sound was not confident, but it was a start.
created_at
"2026-09-03T09:58:12.9Z"
9/3/2026, 9:58:12 AM
model
"deepseek/deepseek-v4-pro-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
875
moderation_latency
(null)
generation_time
59869
tokens_prompt
75
tokens_completion
4108
native_tokens_prompt
67
native_tokens_completion
4345
native_tokens_completion_images
(null)
native_tokens_reasoning
4087
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
service_tier
(null)
usage
0.01729464
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788429492-hUzdR58MA5Wk6AwKDnir"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788429492-lwNLbaWCwR4dRheDTGok"
upstream_id
"0711951f-aws_ue2"
provider_responses
0
endpoint_id
"218b0cec-3278-4b88-8ee0-3f346eccd35f"
id
"0711951f-aws_ue2"
is_byok
false
latency
875
model_permaslug
"deepseek/deepseek-v4-pro-20260813"
provider_name
"Together"
status
200
total_cost
0.01729464
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%